Sentiment lexicon adaptation with context and semantics for the social web

Abstract

Abstract. Sentiment analysis over social streams offers governments and organisations a fast and effective way to monitor the publics' feelings towards policies, brands, business, etc. General purpose sentiment lexicons have been used to compute sentiment from social streams, since they are simple and effective. They calculate the overall sentiment of texts by using a general collection of words, with predetermined sentiment orientation and strength. However, words' sentiment often vary with the contexts in which they appear, and new words might be encountered that are not covered by the lexicon, particularly in social media environments where content emerges and changes rapidly and constantly. In this paper, we propose a lexicon adaptation approach that uses contextual as well as semantic information extracted from DBPedia to update the words' weighted sentiment orientations and to add new words to the lexicon. We evaluate our approach on three different Twitter datasets, and show that enriching the lexicon with contextual and semantic information improves sentiment computation by 3.4% in average accuracy, and by 2.8% in average F1 measure.

DeepSpace: Mood-Based Image Texture Generation for Virtual Reality from Music

“…Emotional Responses. While the qualitative responses correlate well with our hypothesis, in order to get a quantitative measure of the text responses, we use the NRC Emolex dataset [37]. We have each user's textual responses to the two questions about how the song and the VE made them feel.…”

The Construction of Sentiment Lexicon Based on Context-Dependent Part-of-Speech Chunks for Semantic Disambiguation

“…Some attempts have been made to prevent the sentimental ambiguity problem in the construction of sentiment lexicon. In 2017, Saif et al [37] used context and semantic information extracted from specific domains to update the sentiment tendency of words and to alleviate the difference in lexical sentiment when context changes. Later, Han et al [38] used mutual information with POS to generate a sentiment lexicon for the specific domain and achieved good results in sentiment analysis tasks.…”

Unsupervised Genre-Based Multidomain Sentiment Lexicon Learning Using Corpus-Generated Polarity Seed Words

“…Mutual information between SentiWordNet synsets and labeled corpora was explored to learn a sentiment lexicon [33]. In another approach, Thelwall lexicon and a two-dimensional transformed vector representation were used to calculate sentiment scores [34]. This method learned the sentiment scores and expanded the existing lexicon.…”